open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Releases Activity

chore(catalog): release llm-security v7.8.0 — bump ref + README, refresh rollout brief

Browse source 
llm-security cut v7.8.0 (TRG/SIG/AST deep-scan scanners) and tagged `v7.8.0`
(commit 6d3c4b5) in its repo. Sync the marketplace coordinator:

- .claude-plugin/marketplace.json: source.ref v7.7.2 → v7.8.0 (installs track the
  real release; version-consistency gate → OK for llm-security).
- README.md: version label v7.7.2 → v7.8.0; scanner count 23 → 26 (+3: TRG/SIG/AST)
  in both the "Deterministic scanning" bullet and the stat line; tests 1822 → 1863.
- docs/state-version-rollout.md: mark llm-security STATE.md row DONE (it is tracked,
  not gitignored), add the missing playground-design-system row, and refresh the
  Workstream B run note (8 OK / 2 WARN; llm-security resolved this day).

Gate: `node scripts/check-versions.mjs` → 8 OK, 2 WARN (linkedin-studio,
ms-ai-architect — pre-existing, operator decision), 0 ERROR.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3s6WnubSSrFjAQTLQdVbG
This commit is contained in:
Kjell Tore Guttormsen 2026-06-20 11:58:39 +02:00
commit 843254df5b
3 changed files with 9 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -20,18 +20,18 @@ Each plugin keeps its own full README and CHANGELOG; this page is just the catal
## Plugins
### [LLM Security](https://git.fromaitochitta.com/open/llm-security) `v7.7.2`
### [LLM Security](https://git.fromaitochitta.com/open/llm-security) `v7.8.0`
Security scanning, auditing, and threat modeling for agentic AI projects. Built on OWASP LLM Top 10 (2025), OWASP Agentic AI Top 10, and Google DeepMind's AI Agent Traps taxonomy.
- **Automated enforcement** — 9 hooks block prompt injection, secrets in code, destructive commands, and supply-chain risks in real time
- **Deterministic scanning** — 23 Node.js scanners for entropy, Unicode codepoints, typosquatting, taint flow, git forensics, AI-BOM, and IDE-extension prescan (VS Code + JetBrains)
- **Deterministic scanning** — 26 Node.js scanners for entropy, Unicode codepoints, typosquatting, taint flow, git forensics, AI-BOM, trigger/signature/AST-taint, and IDE-extension prescan (VS Code + JetBrains)
- **Advisory analysis** — 20 commands that scan, audit, and model threats with letter-graded reports and remediation
- **Enterprise governance** — EU AI Act / NIST AI RMF / ISO 42001 mapping, SARIF 2.1.0 output, policy-as-code, standalone CLI
Key commands: `/security posture`, `/security audit`, `/security scan`, `/security ide-scan`, `/security threat-model`
6 agents · 23 scanners · 9 hooks · 1822 tests · [Full documentation →](https://git.fromaitochitta.com/open/llm-security)
6 agents · 26 scanners · 9 hooks · 1863 tests · [Full documentation →](https://git.fromaitochitta.com/open/llm-security)
---